How to Use the Clearbit (HubSpot) MCP in LlamaIndex

Q: How can I make Clearbit (HubSpot) data searchable with LlamaIndex?

Use the McpToolSpec to load the tools. When your agent calls a tool like getprospects, you can configure LlamaIndex to automatically ingest the returned company data into your vector index for future queries.

Q: Can I filter which tools my agent can use?

Yes, the LlamaIndex adapter supports an allowedtools filter. You can restrict your agent to only use specific functions, like findperson, to control costs and scope.

Index Clearbit data directly into your LlamaIndex knowledge base. Ground your RAG app in real-time company and person info.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clearbit (HubSpot) MCP to LlamaIndex

Create your Vinkius account to connect Clearbit (HubSpot) to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Clearbit (HubSpot) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a Live Company Knowledge Base

This server gives your LlamaIndex agent tools to fetch company data. You can use tools like `find_company` or `get_watchlist` and have the agent automatically index the results into a vector store. Now your RAG application isn't just searching static documents. When you ask, "What do we know about example.com?", the agent can query its index of previously fetched Clearbit profiles. It's a living database of your B2B intelligence, powered by this MCP Server.

Augment Queries with Person Data

The `find_person` and `find_person_and_company` tools let your agent look up contacts by email. With LlamaIndex, the agent can use this data to add context to its answers. Imagine asking your agent, "Summarize my last interaction with jane@example.com." The agent can use `find_person` to get Jane's title and company, then combine that with data from your other documents to give a much richer answer. This MCP tool output becomes queryable context.

Ground Responses with Your LlamaIndex MCP Server

Stop your agent from making up facts about companies or people. By giving it access to this server, it can use `reveal_ip` or `autocomplete_company` to get facts first. LlamaIndex excels at this. You can configure your query engine to call a Clearbit tool if the answer isn't in the existing knowledge base. This keeps your agent's responses grounded in fresh, accurate data straight from the source.

Setup guide

Set up Clearbit (HubSpot) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Clearbit (HubSpot) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Clearbit (HubSpot) tools.",
)
response = await agent.run("List recent Clearbit (HubSpot) data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Clearbit (HubSpot). All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Clearbit (HubSpot) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Clearbit (HubSpot) MCP in LlamaIndex

Use the `McpToolSpec` to load the tools. When your agent calls a tool like `get_prospects`, you can configure LlamaIndex to automatically ingest the returned company data into your vector index for future queries.

Yes. You can set up a FunctionAgent that analyzes a query and determines if it needs fresh data. If so, it will call the appropriate Clearbit (HubSpot) tool, like `find_company`, before synthesizing the final answer.

It lets you blend static knowledge with live, dynamic data. Your RAG application can answer questions using both your internal documents and up-to-the-minute company information from the Clearbit (HubSpot) MCP Server.

Yes, the LlamaIndex adapter supports an `allowed_tools` filter. You can restrict your agent to only use specific functions, like `find_person`, to control costs and scope.

Your LlamaIndex agent makes requests for person and company data through the Vinkius platform, which isolates each call. The data you choose to index is stored in your own vector database, giving you control over its lifecycle. The MCP server itself doesn't persist the results.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript